Taxonomy Induction

Latest papers

16 papers2 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

Uncovering Semantic Hierarchies in Text-Attributed Graphs via Variational EM-based LLM-GNN Synergy
Oct 17, 2026Yunhui Liu, Xudong Jin, Qizhuo Xie +5Text-Attributed Graph Learning Hierarchical Representation Learning
State Key Laboratory for Novel Software Technology, Nanjing University · Department of Statistics, University of Wisconsin–Madison · National Engineering Laboratory for Big Data Analysis and Applications, Peking University
From Plausible Hierarchies to Useful Taxonomies: Evaluating Agentic Harnesses on Customer Feedback
Oct 7, 2026Prabhath Chellingi, Raviraja G, Viraj BagalTaxonomy Induction Automated Evaluation
Enterpret
Towards Automatic Evolution Tree Generation from Citation Graphs
Sep 9, 2026Zexing Zhao, Yuntong Hu, Liang ZhaoCitation Network Analysis Bibliometric Analysis
School of Mechanical Engineering, Georgia Institute of Technology · Department of Computer Science, Emory University
SPARROW: Scalable Taxonomy Induction via Structure-Preserving Partitioning and Constraint-Guided Merging
Sep 7, 2026Yirui Zhang, Yixuan Tang, Yandong Sun +2Spectral Clustering Taxonomy Induction
School of Computing, National University of Singapore
Autoresearch for Marketplace Catalogs: From Legacy Forms to AI-Native Matching
Aug 31, 2026Kartik Ravisankar, Hojat Abdolanezhad, Daniel Capo +3User Preference Modeling Generative AI Evaluation
Thumbtack · San Francisco, CA, USA
TaxCE : A Framework for Automated Taxonomy Construction and Evaluation at Scale
Aug 31, 2026Sandeep Sricharan Mukku, Albert Aristotle Nanda, Rohit PyatiTopic Modeling Semantic Mapping
Amazon
Security and Privacy Taxonomy Generation from Mobile App Reviews
Aug 10, 2026Moghis Fereidouni, Krishna Upadhyay, Umar Farooq +1Cybersecurity Taxonomy Induction
University of Kentucky · Louisiana State University
Fantastic Adaptive Taxonomies and How to Use Them
Jul 17, 2026Mert Cemri, Andrei Cojocaru, Melissa Pan +9Agent Failure Analysis LLM Agent Evaluation
University of California, Berkeley · Apple · Bespoke Labs
Term-Centric Hierarchy Induction from Heterogeneous Corpora
Jun 25, 2026Elena Senger, Yuri Campbell, Jan-Peter Bergmann +2Clustering Hierarchical Clustering
1MaiNLP, Center for Information and Language Processing, LMU Munich, Germany · 2Fraunhofer Institute for Systems and Innovation Research ISI, Germany · Department of Computer Science, IT University of Copenhagen, Denmark
ATLAS: Agentic Taxonomy of Large-Scale Software Ecosystems
Jun 19, 2026Junyi Lu, Mengyao Lyu, Jiahui Wu +6Software Engineering Hierarchical Classification
Institute of Software, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Nanyang Technological University, Singapore +2
TaBIIC2: Interactive Building of Ontological Taxonomies using Weighted Self-Organizing Maps
May 24, 2026Mathieu d'AquinSelf-Organizing Maps Ontology Learning
MosAIK Team, LORIA,MayCNRS,2026Universit´e de Lorraine
Building a Custom Taxonomy of AI Skills and Tasks from the Ground Up with Job Postings
May 20, 2026Stephen Meisenbacher, Peter NorlanderSemantic Mapping Taxonomy Induction
Technical University of Munich Garching, Germany · Loyola University Chicago Chicago, IL, USA
SC-Taxo: Hierarchical Taxonomy Generation under Semantic Consistency Constraints using Large Language Models
May 1, 2026Shiqiang Cai, Nianhong Niu, Shizhu He +2Hierarchical Representation Learning Taxonomy Induction
Institute of Automation, Chinese Academy of Sciences, Beijing, China · University of Science and Technology Beijing, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
BoostTaxo: Zero-Shot Taxonomy Induction via Boosting-Style Agentic Reasoning and Constraint-Aware Calibration
Apr 3, 2026Yancheng Ling, Zhenlin Qin, Leizhen Wang +1Taxonomy Induction Zero-Shot Learning
KTH Royal Institute of Technology, 11428 Sweden · Monash University, Clayton, Australia, 3800
EvoTaxo: Building and Evolving Taxonomy from Social Media Streams
Mar 20, 2026Yiyang Li, Tianyi Ma, Yanfang YeTaxonomy Induction Hierarchical Classification
University of Notre Dame
Learning Hierarchical Knowledge in Text-Rich Networks with Taxonomy-Informed Representation Learning
Mar 9, 2026Yunhui Liu, Yongchao Liu, Yinfeng Chen +3Taxonomy Induction Hierarchical Representation Learning
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · Ant Group, Hangzhou, China · Ant Group, Beijing, China

Oct 17, 2026J/K move · Enter open · S save

Uncovering Semantic Hierarchies in Text-Attributed Graphs via Variational EM-based LLM-GNN Synergy

Yunhui Liu, Xudong Jin, Qizhuo Xie, Chunhui Zhao+4

State Key Laboratory for Novel Software Technology, Nanjing University · Department of Statistics, University of Wisconsin–Madison · National Engineering Laboratory for Big Data Analysis and Applications, Peking University

Text-Attributed Graph Learning Hierarchical Representation Learning Taxonomy Induction LLMs for Graph Learning

Open paper AskPDF arXiv

While hierarchical structures are intrinsic to organizing human knowledge, current representation learning on text-attributed graphs predominantly operates on flat semantic spaces, overlooking the rich coarse-to-fine granularity inherent in real-world data. To bridge this gap, we propose SHiFT, which synergizes the reasoning power of LLMs with the structural representation capability of GNNs within an Expectation-Maximization (EM) paradigm. In the E-step, we harness LLMs as expert taxonomists to induce an explicit semantic tree, introducing a lightweight Mapping & Diagnosis strategy that reduces inference costs by surgically updating the hierarchy only when anomalies are detected. In the M-step, we align the GNN encoder with this induced hierarchy from complementary perspectives, including clustering partition, topological skeleton, and semantic concepts. Theoretical analysis interprets SHiFT as a generalized Variational EM algorithm. Extensive experiments demonstrate that SHiFT not only achieves state-of-the-art performance but also uncovers high-quality, human-readable taxonomies. Our code can be found at https://github.com/Cloudy1225/SHiFT.